Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices

TL;DR

This paper introduces an OCR-based pipeline that effectively extracts structured table data from invoices, enhancing accuracy and robustness for financial automation and archiving tasks.

Contribution

It presents a novel combination of OCR and custom post-processing techniques specifically designed for noisy and non-standard invoice formats.

Findings

Improved accuracy in table data extraction from invoices.

Robustness to noisy and non-standard invoice formats.

Supports real-world financial workflows.

Abstract

This paper presents the design and development of an OCR-powered pipeline for efficient table extraction from invoices. The system leverages Tesseract OCR for text recognition and custom post-processing logic to detect, align, and extract structured tabular data from scanned invoice documents. Our approach includes dynamic preprocessing, table boundary detection, and row-column mapping, optimized for noisy and non-standard invoice formats. The resulting pipeline significantly improves data extraction accuracy and consistency, supporting real-world use cases such as automated financial workflows and digital archiving.