Overview of TruCap+ process stages

Uploaded

Documents/files/images received from different sources are initially uploaded and stored at the designated input source location. Once uploaded, the files proceed to the next stage.

Barcodes identified

This stage identifies any barcodes present in the uploaded document, preparing them for further processing.

Object identification

A crucial process where various key elements within documents are recognized and processed. This stage involves the identification of class types, logos, removal of stamps, recognition of receipts, and extraction of tables.

Objects identified

Class identification, logo identification, stamp removal, receipt identification, and table extraction occur in this stage.

Preprocess init completed

Initiates image pre-processing and document classification using Machine Learning (ML) and Deep Learning (DL) algorithms.

Shadow removed

The removal of shadows from documents enhances data legibility, ensuring clear extraction.

Ready for processing

Uploaded documents are prepared for data extraction and further processing.

Source identified

Document source identification takes place in this stage, setting the document up for further processing.

Pre-processing

Utilizing ML and DL algorithms, image pre-processing and document classification enhance image quality.

Document type identified

Document type identification is performed in this stage, directing documents toward appropriate processing.

Extract data

Based on field ontologies, including synonyms, validations, custom validations, and more, data is extracted using predefined extraction parameters.

Extraction completed

This stage marks the completion of data extraction from the documents.

OCR processing

Optical Character Recognition (OCR) and ML technologies digitize documents, extracting relevant information.

Auto-split completed

Multi-page documents are automatically split and prepared for processing.

Needs manual handling

Documents not meeting validation or Region of Interest (ROI) criteria require manual intervention.

Ready for quality check

After manual processing, documents undergo quality checks and are approved for the next stage of data export.

Needs manual splitting

Multi-page documents undergo automatic splitting based on splitter fields, followed by processing of identified segments.

Ready to export

Documents are prepared for export, awaiting user approval for data export.

Document rejected

Rejected documents are moved to the exception folder specified in the input source location.

Document exported

Documents ready for approval are exported to the designated output source.

Export file created

Captured data is exported in the specified format to the output source assigned to the document subtype.

Document split discarded

Indicates that the split document is discarded.

Document discarded

Indicates that the document is discarded.

Integrated validation

During this stage, the system applies an array of validation techniques, including custom validations, regular expressions, and predefined validation rules. By thoroughly assessing the extracted data against these criteria, TruCap+ guarantees that the captured information adheres to predefined standards.