GROUPED.md

Awesome receipt data extraction

This repository contains resources helpful if you are going to build a system for fiscal receipt data extraction.

Documents grouped in various categories

Full pipeline for extracting key information from photos of receipts

• Receipts2Go: The Big World of Small Documents
• Deep Learning for automatic sale receipt understanding
• From one group of authors:
  • OCR Engine to extract Food-items and Prices from Receipt Images via Pattern matching and heuristics approach
  • OCR Engine to Extract Food-Items, Prices, Quantity, Units from Receipt Images, Heuristics Rules Based Approach
  • Optical Character Recognition Engine to extract Food-items and Prices from Grocery Receipt Images via Templating and Dictionary-Traversal Technique
• Automated Receipt Image Identification, Cropping, and Parsing
• Separation and Extraction of Valuable Information From Digital Receipts Using Google Cloud Vision OCR

Full pipeline for extracting key information from scanned receipts

• Optical Character Recognition on supermarket receipts

Pipeline for OCR from photos of receipts w/o semantic analysis

• A Novel Machine Learning Based Approach for Retrieving Information from Receipt Images

• Receipt automatic reader

Pipeline for OCR from scanned receipts w/o semantic analysis

• Deep Learning Approach for Receipt Recognition

Preprocessing for photos of receipts

• Preprocessing Photos of Receipts for Recognition

• A document detection technique using convolutional neural networks for optical character recognition systems

Preprocessing for various type of documents

• OCR accuracy improvement on document images through a novel pre-processing approach
• Mobile Scanner and OCR (A first step towards receipt to spreadsheet)

Text detection

• Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

Text detection and recognition

• A Novel Integrated Framework for Learning both Text Detection and Recognition
• A Multitask Network for Localization and Recognition of Text in Images
• Towards Unconstrained End-to-End Text Spotting

OCR on documents

• Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation

Semantic analysis

• Utilize OCR text to extract receipt data and classify receipts with common Machine Learning algorithms
• Chargrid: Towards Understanding 2D Documents
• Graph Convolution for Multimodal Information Extraction from Visually Rich Documents
• Visual-Linguistic Methods for Receipt Field Recognition
• CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor
• Attend, Copy, Parse End-to-end Information Extraction from Documents
• End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net
• EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
• Post-OCR parsing: building simple and robust parser via BIO tagging
• LayoutLM: Pre-training of Text and Layout for Document Image Understanding