A Survey of Deep Learning Approaches for OCR and Document Understanding

2020/11/27 by Nishant Subramani, Alexandre Matton, Subramani, Nishant +5 · 5 citations
Computer Science · #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Natural Language Processing Techniques

paper · pdf · doi:10.48550/arxiv.2011.13534

openalex publication_date 2020/11/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Documents are a core part of many businesses in many fields such as law, finance, and technology among others. Automatic understanding of documents such as invoices, contracts, and resumes is lucrative, opening up many new avenues of business. The fields of natural language processing and computer vision have seen tremendous progress through the development of deep learning such that these methods have started to become infused in contemporary document understanding systems. In this survey paper, we review different techniques for document understanding for documents written in English and consolidate methodologies present in literature to act as a jumping-off point for researchers exploring this area.

Citations

• Synthetic Data and Artificial Neural Networks for Natural Scene Text\n Recognition
• Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
• Sequence to Sequence Learning with Neural Networks
• ImageNet classification with deep convolutional neural networks
• YOLOv3: An Incremental Improvement
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Reformer: The Efficient Transformer
• Rethinking Attention with Performers

Cited by

• Robustness of Structured Data Extraction from Perspectively Distorted Documents
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
• DocReward: A Document Reward Model for Structuring and Stylizing
• Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing
• Finding Needles in Images: Can Multimodal LLMs Locate Fine Details?

Related

• Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review
• DLUE: Benchmarking Document Language Understanding
• Unfolding the Structure of a Document using Deep Learning
• Deep Reader: Information extraction from Document images via relation extraction and Natural Language
• Document AI: Benchmarks, Models and Applications