A Machine Learning Framework for Data Ingestion in Document Images
arXiv:2003.00838
Abstract
Paper documents are widely used as an irreplaceable channel of information in many fields, especially in financial industry, fostering a great amount of demand for systems which can convert document images into structured data representations. In this paper, we present a machine learning framework for data ingestion in document images, which processes the images uploaded by users and return fine-grained data in JSON format. Details of model architectures, design strategies, distinctions with existing solutions and lessons learned during development are elaborated. We conduct abundant experiments on both synthetic and real-world data in State Street. The experimental results indicate the effectiveness and efficiency of our methods.
References in corpus (11)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- SphereFace: Deep Hypersphere Embedding for Face Recognition
- Rosetta: Large scale system for text detection and recognition in images
- Light-Head R-CNN: In Defense of Two-Stage Object Detector
- Multi-Oriented Text Detection with Fully Convolutional Networks
- On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
- Deep Direct Regression for Multi-Oriented Scene Text Detection
- Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
- Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
- One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis