LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
复制标题
DOI：
10.1007/978-3-030-86549-8_9
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Zejiang Shen;Ruochen Zhang;Melissa Dell;Benjamin Charles Germain Lee;Jacob Carlson;Weining Li
中科院分区：
文献类型：
--
作者：
Zejiang Shen;Ruochen Zhang;Melissa Dell;Benjamin Charles Germain Lee;Jacob Carlson;Weining Li
文档图像分析（DIA）的最新进展主要是由神经网络的应用推动的。理想情况下，研究成果可以很容易地部署在生产中，并扩展到进一步的调查。然而，各种因素，如松散组织的代码库和复杂的模型配置复杂的重要创新容易重用的广泛受众。尽管在自然语言处理和计算机视觉等学科中一直在努力提高可重用性和简化深度学习（DL）模型开发，但没有一个是针对DIA领域的挑战进行优化的。这是现有工具包中的一个主要差距，因为DIA是社会科学和人文科学广泛学科学术研究的核心。本文介绍了LayoutParser，一个开源库，用于简化DIA研究和应用中DL的使用。coreLayoutParserlibrary提供了一组简单直观的界面，用于应用和自定义DL模型，以执行布局检测、字符识别和许多其他文档处理任务。为了提高可扩展性，LayoutParser还集成了一个社区平台，用于共享预训练模型和完整的文档数字化管道。我们证明了LayoutParser在实际用例中对轻量级和大规模数字化管道都有帮助。图书馆的网址为 https://layout-parser.github.io .
Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of important innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introducesLayoutParser, an open-source library for streamlining the usage of DL in DIA research and applications. The coreLayoutParserlibrary comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout detection, character recognition, and many other document processing tasks. To promote extensibility,LayoutParseralso incorporates a community platform for sharing both pre-trained models and full document digitization pipelines. We demonstrate thatLayoutParseris helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io .