Character extraction from natural scene images by hierarchical classifiers
Character extraction from natural scene images by hierarchical classifiers
复制标题
DOI：
10.1109/icpr.2004.1334352
复制
发表时间：
2004-08
期刊：
影响因子：
--
通讯作者：
Takuma Yamaguchi;M. Maruyama
中科院分区：
文献类型：
--
作者：
Takuma Yamaguchi;M. Maruyama
提出了一种利用分层分类器提取自然场景图像中特征区域的方法。该层次结构由两种类型的分类器：基于直方图的分类器和SVM。在底层，快速和可靠的基于直方图的分类器被用来拒绝明显的非字符区域。在下一个层次上，利用非线性SVM来做出最终决策。非线性SVM的一个缺点是其计算成本。为了减少计算量，我们使用稀疏小波表示。此外，为了进一步降低成本，我们提出了一种方法来近似支持向量机与稀疏的支持向量。我们的实验表明，这种两步方法可以执行非常好的计算成本和识别率。
This paper proposes a method to extract character regions in natural scene images by hierarchical classifiers. The hierarchy consists of two types of classifiers: histogram based classifier and SVM. On the bottom level, fast and reliable histogram based classifier is used to reject apparent non-character regions. On the next level, a non-linear SVM is exploited to make a final decision. One of the drawbacks of non-linear SVMs is its computational cost. To reduce the computational cost, we use sparse wavelet representation. Moreover, to reduce the cost further, we propose a method to approximate a SVM with sparse support vectors. We experimentally show this two-step method can perform very well with respect to both the computational cost and recognition rate.