arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1710.03006cs.CL
收藏

结合文本和视觉特征的卷积神经网络页面流分割

Page Stream Segmentation with Convolutional Neural Nets Combining Textual and Visual Features

Leipzig University(莱比锡大学)

Gregor Wiedemann, Gerhard Heyer

摘要:

近年来,纸质文件的(逆向)数字化已成为私人和公共档案馆的一项主要任务,也是电子邮件收发室应用程序的一项重要任务。作为第一步,工作流程涉及文档的扫描和光学字符识别(OCR)。在这种情况下,保存单页扫描的文档上下文是一个主要要求。为了简化涉及大量纸张扫描的工作流程,页面流分割(PSS)是将扫描图像流自动分离为多页文档的任务。在与德国联邦档案馆的数字化项目中,我们开发了一种基于卷积神经网络(CNN)的新方法,结合图像和文本特征,以实现最佳的文档分离结果。评估表明,我们的PSS架构实现了高达93%的准确性,这可以被视为一个新的国家的最先进的这项任务。

英文摘要:

In recent years, (retro-)digitizing paper-based files became a major undertaking for private and public archives as well as an important task in electronic mailroom applications. As a first step, the workflow involves scanning and Optical Character Recognition (OCR) of documents. Preservation of document contexts of single page scans is a major requirement in this context. To facilitate workflows involving very large amounts of paper scans, page stream segmentation (PSS) is the task to automatically separate a stream of scanned images into multi-page documents. In a digitization project together with a German federal archive, we developed a novel approach based on convolutional neural networks (CNN) combining image and text features to achieve optimal document separation results. Evaluation shows that our PSS architecture achieves an accuracy up to 93 % which can be regarded as a new state-of-the-art for this task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑