Text Extraction from Scene Images by Character Appearance and Structure Modeling.
Text Extraction from Scene Images by Character Appearance and Structure Modeling.
复制标题
DOI：
10.1016/j.cviu.2012.11.002
复制
发表时间：
2013-02-01
影响因子：
4.5
通讯作者：
Tian, Yingli
中科院分区：
文献类型：
--
作者：
Yi, Chucai;Tian, Yingli
关键词：
本文提出了一种从自然场景图像中检测文本信息的新算法。场景文本的分类和检测仍然是一个开放的研究课题。我们提出的算法能够同时对字符外观和结构进行建模，以生成具有代表性和区别性的文本描述符。本文的主要贡献包括三个方面：1)提出了一种新的基于结构相关算法的字符外观模型，该算法从检测到的字符样本兴趣点提取可区分的外观特征；2)提出了一种新的基于结构和相关性的文本描述子，通过字符样本之间的结构差异和结构成分的共现来建模字符结构；3)结合颜色分解、字符轮廓细化和字符串线对齐的文本区域定位方法，对候选字符进行定位，并对检测到的文本区域进行细化。我们进行了三组实验，包括文本分类、文本检测和字符识别，以评估该算法的有效性。在基准数据集上的评估结果表明，该算法在场景文本分类和检测上达到了最先进的性能，并显著优于现有的字符识别算法。
In this paper, we propose a novel algorithm to detect text information from natural scene images. Scene text classification and detection are still open research topics. Our proposed algorithm is able to model both character appearance and structure to generate representative and discriminative text descriptors. The contributions of this paper include three aspects: 1) a new character appearance model by a structure correlation algorithm which extracts discriminative appearance features from detected interest points of character samples; 2) a new text descriptor based on structons and correlatons, which model character structure by structure differences among character samples and structure component co-occurrence; and 3) a new text region localization method by combining color decomposition, character contour refinement, and string line alignment to localize character candidates and refine detected text regions. We perform three groups of experiments to evaluate the effectiveness of our proposed algorithm, including text classification, text detection, and character identification. The evaluation results on benchmark datasets demonstrate that our algorithm achieves the state-of-the-art performance on scene text classification and detection, and significantly outperforms the existing algorithms for character identification.
登录
查看更多内容
影响因子：
10.6
作者：
Chen, XL;Yang, J;Waibel, A
通讯作者：
Waibel, A
DOI：
10.1016/0734-189x(89)90116-3
发表时间：
1989-09-01
期刊：
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING
影响因子：
--
作者：
WANG, D;SRIHARI, SN
通讯作者：
SRIHARI, SN
影响因子：
3.3
作者：
Nikolaou, Nikos;Papamarkos, Nikos
通讯作者：
Papamarkos, Nikos
影响因子：
8
作者：
Ojala, T;Pietikainen, M;Harwood, D
通讯作者：
Harwood, D
DOI：
10.1109/tpami.2003.1251157
发表时间：
2003-12-01
影响因子：
23.6
作者：
Kim, KI;Jung, K;Kim, JH
通讯作者：
Kim, JH