文字检测

1、Automated Text Detection and Character Recognition in Natural Scenes Based on Local Image Features and Contour Processing Techniques

abstract：

Various literature based geometrical and contour oriented filters, used to distinguish between text and non-text MSER regions as well as to group remaining text regions into words and phrases, are applied first. Novel filters, designed to reject remaining non-text regions and words (phrases) that are not in line with assumed properties, are utilized next. 

 首先应用各种基于文献的基于几何和轮廓的过滤器，用于区分文本和非文本MSER区域，并将剩余文本区域分组为单词和短语。 接下来使用旨在拒绝剩余的非文本区域和与假定属性不一致的单词（短语）的新颖过滤器。

2、Arbitrary-Oriented Scene Text Detection via Rotation Proposals

abstract：

This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images. We present the Rotation Region Proposal Networks (RRPN), which are designed to generate inclined proposals with text orientation angle information. The angle information is then adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation. The Rotation Region-of-Interest (RRoI) pooling layer is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. The whole framework is built upon a region-proposal-based architecture, which ensures the computational efficiency of the arbitrary-oriented text detection compared with previous text detection systems.

本文介绍了一种新颖的基于旋转的自然场景图像中任意导向文本检测框架。 我们提出了旋转区域提议网络（RRPN），其目的是生成带有文本方向角度信息的倾斜提案。 角度信息然后适用于边界框回归，以使得提案在方向上更准确地适合文本区域。 提出旋转兴趣区域（RRoI）池层以将任意导向的提议投影到文本区域分类器的特征映射。 整个框架建立在基于区域提议的架构上，与以前的文本检测系统相比，该架构可确保任意导向的文本检测的计算效率。

3、Cloud of Line Distribution and Random Forest Based Text Detection from Natural/Video Scene Images

abstract：

This paper presents a new method based on Cloud of Line Distribution (COLD) and Random Forest Classifier for text detection in both natural and video images. The proposed method extracts unique shapes of text components by studying the relationship between dominant points such as straight or cursive over contours of text components, which is called COLD in polar domain. 

本文提出了一种基于云分布线（COLD）和随机森林分类器的自然和视频图像文本检测新方法。 所提出的方法通过研究文本成分的直线或草写轮廓等主要点之间的关系，在极域中称为COLD，提取文本成分的独特形状。

4、Arbitrary-Oriented Scene Text Detection viaRotation Proposals

https://arxiv.org/pdf/1703.01086.pdf

abstract：

This paper introduces a novel rotation-based frameworkfor arbitrary-oriented text detection in natural scene images.

旋转框架的文字检测