Awesome

Information extraction from Image using Deep learning

Research paper and code on information extraction from image/pdf

Layout Analysis in Document/Image:

Document layout analysis is the process of identifying and categorizing the regions of interest in the scanned image of a text document. A reading system requires the segmentation of text zones from non-textual ones and the arrangement in their correct reading order.Detection and labeling of the different zones (or blocks) as text body, illustrations, math symbols, and tables embedded in a document is called geometric layout analysis.(https://en.wikipedia.org/wiki/Document_layout_analysis)

• PubLayNet
• PRIMA
• HJDatasets (Historical Japanese Documents with Complex Layouts)
• Newspaper Navigator
• TableBank
• DocBank
• German-Brazilian Newspapers (GBN) Dataset

Tools:

• layout parsing
• Detectron 2
• Parsr
• DeepDocDetection

INVOICE EXTRACTION

• PICK Pytorch
• PICK
• Graph net

RECEIPT DATA

• CORD: A Consolidated Receipt Dataset for Post-OCR Parsing

Datasets

• TableBank
• DocBank
• FUNSD
• RVL-CDIP
• SROIE
• Document Visual Question Answering
• HTR Dataset ICFHR 2016
• Tobacco3482
• PubLay
• Tobacco800 Complex Document Image Database and Groundtruth
• NIST Forms

Code:

• Layoutlm
• Graph Convolution on Structured Documents
• Graph Matric
• Feature Extraction from Graph
• Extract data from Invoice
• CascadeTabNet
• Tabulo
• PubLayNet
• InvoiceNet Extract text from invoice
• Cutie

Research Papers

• LayoutLM
• PICK
• Deep Convolutional Nets for Document Image Classification and Retrieval
• Table Detection in Invoice Documents by Graph Neural Network
• Graph Convolution on Structured Documents
• PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
• Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval
• Few-Shot Learning with Graph Neural Networks
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Efficient, Lexicon-Free OCR using Deep Learning
• An Overview of the Tesseract OCR Engine
• Semi-Supervised Classification with Graph Convolutional Networks
• An Invoice Reading System Using a Graph Convolutional Network
• Spatial Dependency Parsing for Semi-Structured Document Information Extraction

DETECT TABLE in Image/PDF

• CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents
• TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images
• RetinaNet

Reference

• parsing pdf