arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.02576cs.CV
收藏

深度视觉无模板表单解析

Deep Visual Template-Free Form Parsing

Brigham Young University(杨百翰大学);Adobe Research(奥多比研究院)

Brian Davis, Bryan Morse, Scott Cohen, Brian Price, Chris Tensmeyer

摘要:

由于表单布局的多样性,从表单图像中自动、无模板地提取信息是一项挑战。由于噪音和退化,这对于历史形式来说更具挑战性。提取过程的一个关键部分是将输入文本与预先打印的标签相关联。我们提出了一个学习的,无模板的解决方案来检测预打印文本和输入文本/手写,并预测它们之间的成对关系。虽然以前的方法来解决这个问题一直集中在干净的图像和清晰的布局,我们表明我们的方法是有效的噪声,退化和不同形式的图像域。我们引入了一个新的历史形态图像数据集(19世纪末,20世纪初)来训练和验证我们的方法。我们的方法使用卷积网络来检测预打印文本和输入文本行。我们从检测网络中汇集特征,以与语言无关的方式对可能的关系进行分类。我们表明,我们提出的配对方法优于启发式规则,视觉特征是获得高精度的关键。

英文摘要:

Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts. This is even more challenging for historical forms due to noise and degradation. A crucial part of the extraction process is associating input text with pre-printed labels. We present a learned, template-free solution to detecting pre-printed text and input text/handwriting and predicting pair-wise relationships between them. While previous approaches to this problem have been focused on clean images and clear layouts, we show our approach is effective in the domain of noisy, degraded, and varied form images. We introduce a new dataset of historical form images (late 1800s, early 1900s) for training and validating our approach. Our method uses a convolutional network to detect pre-printed text and input text lines. We pool features from the detection network to classify possible relationships in a language-agnostic way. We show that our proposed pairing method outperforms heuristic rules and that visual features are critical to obtaining high accuracy.

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。

↑