论文标题
破碎的新闻：使报纸可访问以打印受损
Broken News: Making Newspapers Accessible to Print-Impaired
论文作者
论文摘要
访问每日新闻内容仍然是有印刷障碍的人的巨大挑战，包括盲人和低视觉，由于印刷内容的不透明性和在线资源的阻碍。在本文中，我们将印刷报纸数字化的方法介绍为诸如HTML之类的可访问文件格式。我们使用实例细分和检测框架进行报纸布局分析，然后使用OCR来识别文本元素，例如标题和文章文本。此外，我们为Mask-RCNN框架提出了Edgemask损耗函数，以改善分割掩码边界，从而准确下游OCR任务。从经验上讲，我们表明我们提出的损失函数将新闻文章文本的单词错误率（WER）降低了32.5％。
Accessing daily news content still remains a big challenge for people with print-impairment including blind and low-vision due to opacity of printed content and hindrance from online sources. In this paper, we present our approach for digitization of print newspaper into an accessible file format such as HTML. We use an ensemble of instance segmentation and detection framework for newspaper layout analysis and then OCR to recognize text elements such as headline and article text. Additionally, we propose EdgeMask loss function for Mask-RCNN framework to improve segmentation mask boundary and hence accuracy of downstream OCR task. Empirically, we show that our proposed loss function reduces the Word Error Rate (WER) of news article text by 32.5 %.
