Strokelets: A Learned Multi-scale Representation for Scene Text Recognition
Strokelets: A Learned Multi-scale Representation for Scene Text Recognition
复制标题
DOI：
10.1109/cvpr.2014.515
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
C. Yao;X. Bai;Baoguang Shi;Wenyu Liu-
中科院分区：
文献类型：
--
作者：
C. Yao;X. Bai;Baoguang Shi;Wenyu Liu-
在广泛应用的推动下，场景文本检测与识别已成为计算机视觉领域活跃的研究课题。尽管研究广泛，但由于各种干扰因素，在不受控制的环境中定位和阅读文本仍然极具挑战性。本文提出了一种新的场景文本识别的多尺度表示方法。这种表示由一组可检测的原语组成，这些原语被称为笔画，它们捕获不同粒度的字符的基本子结构。笔划具有四个显著的优势：(1)可用性：从边界框标签中自动学习；(2)鲁棒性：对干扰因素不敏感；(3)通用性：适用于不同的语言；(4)表达性：有效地描述字符。在标准基准测试上的大量实验验证了笔划的优点，并证明了该算法在文本识别方面的有效性。
Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision. Though extensively studied, localizing and reading text in uncontrolled environments remain extremely challenging, due to various interference factors. In this paper, we propose a novel multi-scale representation for scene text recognition. This representation consists of a set of detectable primitives, termed as strokelets, which capture the essential substructures of characters at different granularities. Strokelets possess four distinctive advantages: (1) Usability: automatically learned from bounding box labels, (2) Robustness: insensitive to interference factors, (3) Generality: applicable to variant languages, and (4) Expressivity: effective at describing characters. Extensive experiments on standard benchmarks verify the advantages of strokelets and demonstrate the effectiveness of the proposed algorithm for text recognition.