Character Recognition in Natural Images
Character Recognition in Natural Images
复制标题
DOI：
10.5220/0001770102730280
复制
发表时间：
2009-02
期刊：
影响因子：
--
通讯作者：
T. D. Campos;Bodla Rakesh Babu;M. Varma
中科院分区：
文献类型：
--
作者：
T. D. Campos;Bodla Rakesh Babu;M. Varma
本文解决了自然场景图像中的字符识别问题。特别是，我们专注于识别传统 OCR 技术无法很好处理的情况下的字符。我们提供了一个包含英语和卡纳达语字符的带注释图像数据库。该数据库包含使用标准相机在印度班加罗尔拍摄的街景图像。该问题在基于视觉词袋表示的对象分类框架中得到解决。我们根据最近邻和 SVM 分类评估各种特征的性能。事实证明，该方法的性能仅使用 15 个训练图像，就可以远远优于商业 OCR 系统。此外，该方法可以受益于综合生成的训练数据，从而无需昂贵的数据收集和注释。
This paper tackles the problem of recognizing characters in images of natural scenes. In particular, we focus on recognizing characters in situations that would traditionally not be handled well by OCR techniques. We present an annotated database of images containing English and Kannada characters. The database comprises of images of street scenes taken in Bangalore, India using a standard camera. The problem is addressed in an object cateogorization framework based on a bag-of-visual-words representation. We assess the performance of various features based on nearest neighbour and SVM classification. It is demonstrated that the performance of the proposed method, using as few as 15 training images, can be far superior to that of commercial OCR systems. Furthermore, the method can benefit from synthetically generated training data obviating the need for expensive data collection and annotation.