About TopSoft SmartCapture Enterprise Edition

• Import
• Recognition
• Verification
• Export

SmartCapture is one of the cost-effective leaders in the line of the products based on the SDP technology and one of the most perspective products in the field of automated document processing for small-to-corporate business. SmartCapture is used for stream data processing and data extraction from documents, both paper-based and graphic files with different formats including the widely used PDF-format.

Extensible SmartCapture architecture allows processing different kinds of forms received from different inputs in the same project, using the same template, rules set and export. More over SmartCapture is used by several companies for joint processing of OCR forms and electronic forms with pre-printed 2D barcodes in the same streams. Rules export system for SmartCapture is being designed, able to export required rules for usage in web server and client-side forms filling application (browsers, Adobe Acrobat Reader for example). This can be achieved pretty easy, since the SmartCapture uses the standard Jscript language for server rules definition, supported by most browsers and other form-filling applications. SmartCapture can be configured to plan and process unified form and rules designing system, able to automatically generate form/rules definitions and graphical representation for both paper (for OCR) and electronic forms, and export rules for the other proposed systems. The system will have the ability to modify different aspects (form image, fields position, etc) for specific form designs (electronic, paper, web), while preserving business logic, generic form rules, and ability to process all kind of forms in one stream.

SmartCapture is a scalable system that can be presented in different types: as a local system and a network system – in such way document processing can be shared by many operators, in this case it will increase a processing speed and total effectiveness.

This system is easy-to-deploy and able to process documents:

• with fixed structure (for example order forms, different forms of questionnaires, annexes, payment requests, educational tests, census or insurance forms, healthcare claims, tax returns , etc);
• half-structured documents (bills, instructions, way-bills, payment orders and requests, etc.);
• documents which normally do not have clear structure (contracts, letters, articles, etc.).

System allows users to extract data from documents: effective and expiration date, customer, sum, supplier, etc. Paper documents can be imported into the system by using scanners or MFPs. The system is designed for a wide range of tasks, from simple recognition of an unlimited volume of text, to complex projects of organizing the required data export into corporate information systems, processing of incoming documentation flow, etc. The need for key operator labor can be reduced by 50 to 70 percent. System allows users to regain their investment quickly—often as soon as in a year when used for high-volume applications. The solution’s intuitive visualization environment requires no programming skills what cuts the costs of software development significantly.

SmartCapture capabilities allow a simultaneous processing of documents of different types recieved from various sources and a simultaneous working with several projects. Specific license configuration will determine which modules are permitted for activation. Processing of documents has 4 stages: import (scanning), recognition (image pre-processing, separation, classification, data/text extraction and validation), verification (rules error correction, assembling error correction, context verification and group verification), export (wide range of formats of verified data and images).

Import Stage paper documents can be imported into the program by using any scanning device (scanners or MFPs) that supports TWAIN scanning protocol. Images of documents can be manually added from a folder or automatically imported by using Hot Folder settings The supported input formats of images include PDF, BMP, PNG, JPEG and TIFF. Import operations can be simplified and automated by using a set of import profiles with pre-defined settings.

Recognition Stage includes image pre-processing, document classification, data and text extraction and automated verification of data. All of these actions are running in automatic mode.

• SmartCapture logically determines the location of data in the documents. The system can find and extract data from any part of a document using any available information: connection of data fields with other elements on a page, field content, its size, etc. - there is no need to put a cover page on each set of documents, and to separate pages between the actual multi-page document and its attachments.

Verification (Correction) Stage. After recognition stage, a data verification stage begins. All data in the recognised fields is getting a recognition status - it can be uncertain recognised characters, certain recognised characters or no data in the fields. So after this definition operator can manually correct all incorrect data or add data to the fields which were recognized as empty. However, manual input of data by operator depends on quality of recognition of paper documents.

Export Stage - after all stages are passed. A wide range of built-in exporters allows the system to transform data into necessary format for the user, from text files to transferring of received information to databases. System supports a wide range of formats to save data (TXT, DBF, CSV and XML) and images (TIFF, JPEG, PDF, PDF/A, BMP, PNG).

SmartCapture capabilities allow the simultaneous processing of documents of different types from various sources and the simultaneous working with several projects. For details about these and other capabilities see Capabilities.

<<Back to top

Simplicity: User interface is designed for optimum usability. Installation of all program modules does not take plenty time and allows get working started with it in short time. System automates processing operations to minimize training requirements and increase efficiency of verification operations. System provides an intuitive, customizable interface that guides operators through each processing step.

Simultaneous multi-project processing and single entry point for any kind of documents: System allows users to bring all types of documents and forms into database without tedious manual data entry. Image pre-processing implies a series of operations to correct the page orientation, invert and remove skewing or noise on images. System automatically analyzes all incoming documents in a batch according to their type and processes them appropriately according to predefined checking rules and template. System is able to process simultaneously single-page and multi-page, structured, semi-structured and unstructured documents with flexible structure, logically determining document type by itself and applying relevant checking rules to it. For example, you can work with phone bills, invoices, irregular form of tax declarations, etc. or simultaneously process and transfer data to various organizations. Customizability: System can be readily integrated with the existing business processes and workflow. An intuitive and ergonomic processing interface allows users to begin integrating data capture into the workflow quickly and seamlessly. Users can script input, output and validation rules and customize verification and validation scenarios to match the unique needs of their particular industry. Password protection: Only one person whose data is entered by the system administrator in the user directory can gain access to data processing within specific projects. Access can be allowed either for all stations, or only for particular ones. Logger: System of statistical data collection allows storing information about each project and about movement of all documents in the specific project, from the moment of document (image file) creation to the export of data received into the external environment. Scalability: the system can be equipped with additional stations without interrupting document processing at any time. For particular tasks the number of stations can be changed. Organizations may choose to start by scanning a single document type in one department and then extend those capabilities to other departments and document types.

The possibility of processing documents received from various sources: The system can be easily integrated with the scheme of corporate information, thus operating as the recipient of information from various sources (scanner, fax, e-mails, etc.) as well as the data provider for other information users in the organization.

Detailed export parameter settings and checking: Existing of document templates matches with imported images and classifies the incoming mix of separate pages to the appropriate documents. Various rules are used: checking format, checking data against database, checking sums, replacing values from the list, normalizing dates and prices, etc. Many data types have associated dictionaries of permitted words for validation purposes. System supports a wide range of formats to save data (TXT, DBF, CSV and XML) and images (TIFF, JPEG, PDF, PDF/A, BMP, PNG).The extracted data can be exported to external databases (via ODBC) or files, transferred to business applications and document management systems. The data can be exported as is, or along with image and text attachments.

Data acquisition using flexible forms technology: Flexible forms technology allows the system to process documents which normally do not have a clear structure, and where data fields’ location varies in different documents. The system logically determines the location of such fields in a document and extracts from them necessary data. Flexible descriptions for semi-structured documents (with the similar types of data but variable layout) are enough to find all required fields in documents coming from different suppliers and with any layout variations.

Data verification: There are three different verification modes: group verification (for checkmarks and digits mostly); field verification (for text field contents); and verification in the Document window. The verification process also includes: correction of assembling rules, correction of validation rules and manual indexing.

Extensibility: The possibility of interaction with the client's external code for rules checking, etc. When necessary, the system is able to check correctness of data received, using a set of external rules developed with regard to client's requests. It guarantees key information required for a client will be 100% true. Any client rules in scripting languages can be applied in addition to the set of pre-defined rules.

Multi-page document processing: The system is able to process multi-page documents, for which the main processing problem is to find in the document flow the end of the previous document and the beginning of the next one. System logic can solve this problem.

<<Back to top

SmartCapture Enterprise Edition. Benefits

• works right out of the box;
• superior recognition accuracy;
• capability to process both single- and multi-page documents;
• capability to find data elsewhere, using any information available: relation to other objects on the page, contents of the field, its size, lines drawn around, etc.;
• extended export settings (PDF, XML, DataBase, TXT, BMP, JPG, TIFF, etc.);
• archiving/document management software with minimal operator's intervention;
• enhanced scan options.