In this paper, we develop a novel unified framework called DeepText for text
region proposal generation and text detection in natural images via a fully
convolutional neural network (CNN). First, we propose the inception region
proposal network (Inception-RPN) and design a set of text characteristic prior
bounding boxes to achieve high word recall with only hundred level candidate
proposals. Next, we present a powerful textdetection network that embeds
ambiguous text category (ATC) information and multilevel region-of-interest
pooling (MLRP) for text and non-text classification and accurate localization.
Finally, we apply an iterative bounding box voting scheme to pursue high recall
in a complementary manner and introduce a filtering algorithm to retain the
most suitable bounding box, while removing redundant inner and outer boxes for
each text instance. Our approach achieves an F-measure of 0.83 and 0.85 on the
ICDAR 2011 and 2013 robust text detection benchmarks, outperforming previous
state-of-the-art results.

本文提出了一种名为 DeepText 的新型文本区域提案生成和文本检测的统一框架，通过卷积神经网络（CNN）实现。通过 Inception-RPN 提出区域提案，引入 ATC 信息和 MLRP 实现文本和非文本分类和准确定位，最终通过迭代边界框投票和筛选算法获得高的召回率。该方法在 ICDAR 2011 和 2013 的检测基准测试中取得了 F-measure 为 0.83 和 0.85 的优异结果，超过了以前的最新研究成果。